Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"

Official Code for RVT-2 and RVT

Unofficial Implementation of Animate Anyone

Your image is almost there!

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

NocoBase is an extensibility-first, open-source no-code/low-code platform for building business applications and enterprise solutions.

[CVPR'24] Official PyTorch Implementation of "Paint-it: Text-to-Texture Synthesis via Deep Convolutional Texture Map Optimization and Physically-Based Rendering"

[CVPR 2024] SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

An Async library for accessing Indian stock broker API and Websockets.

[3DV 2024] Official Repository for "TADA! Text to Animatable Digital Avatars".

[CVPR 2024] Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model

assistant tools for attention visualization in deep learning

StyleMesh optimizes a stylized texture for an indoor scene reconstruction (CVPR2022).

Awesome 3D Stylization - Advances in 3D Neural Stylization

A Physically-based 3D Renderer written in C++

simple terminal UI for git commands

SOTA Semantic Segmentation Models in PyTorch

An Open Source YouTube app for privacy

Focus on prompting and generating

InstantAvatar: Learning Avatars from Monocular Video in 60 Seconds (CVPR 2023)

[AAAI 2024] UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation. UCMCTrack achieves SOTA on MOT17 using estimated camera parameters.

Extract text blocks from a PDF document with each paragraph as a separate line and text being in reading order going from first column from top to bottom and then into second column and then third …

Official implementation of "DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion"

Autoware - the world's leading open-source software project for autonomous driving

Open-source simulator for autonomous driving research.

Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition (CVPR2023)

[ECCV'2024] Gaussian Grouping for open-world Anything reconstruction, segmentation and editing.